Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sports achievements (first place)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     max
    -0.07
    employee
    -0.07
    full
    -0.06
     profound
    -0.06
    norm
    -0.06
    Regular
    -0.06
    .cy
    -0.06
     smokers
    -0.06
    ugas
    -0.06
     providers
    -0.06
    POSITIVE LOGITS
    'LBL
    0.06
     XYZ
    0.06
    ieur
    0.06
    OMUX
    0.06
    민주
    0.06
    十五
    0.06
    ẻ
    0.06
     громад
    0.06
     المنطقة
    0.06
     mạch
    0.06
    Act Density 0.004%

    No Known Activations